Incentivized Personalized Coordinated Freight Routing Considering System Optimization With Driver-in-Loop Utility Learning
- 6 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (6) , 6919-6931
Abstract
With the growth of cities and the expansion of urban populations, traffic congestion has become a major challenge in urban areas. Congestion significantly worsens economic and environmental conditions, and is particularly problematic in areas with heavy truck traffic. In this paper, we introduce a coordinated freight routing system aimed at optimizing the overall utility of the network and alleviating congestion through personalized routing instructions and incentives. This system specifically tailors the allocation of incentives and payments to individual drivers, considering both current traffic conditions and their specific routing pReferences. We employ a mixed logit model with a linear utility specification to model drivers’ route choice preferences and decisions. Participation in the system is voluntary, and the system ensures that for most drivers, the combined expected utility, including incentives, surpasses their anticipated utility under User Equilibrium (UE), thereby motivating a substantial number of drivers to follow the assigned routes. The system collects data on the drivers’ routing choices, subsequently updating estimates of utility parameters based on their recent decisions. Ahierarchical Bayes estimator is used for the estimation of individual-specific utility parameters. By integrating driver behavior into the routing process, our system actively adapts and updates parameters in response to real driver actions, offering a dynamic and accurate representation of evolving driver preferences. Numerical experiments on the Sioux Falls network demonstrate the effectiveness of the proposed method.Keywords
Funding Information
- National Science Foundation (CNS-1932615)
This publication has 31 references indexed in Scilit:
- Personalized Pareto-improving pricing-and-routing schemes for near-optimum freight routing: An alternative approach to congestion pricingTransportation Research Part C: Emerging Technologies, 2021
- Personalized incentive-based peak avoidance and drivers’ travel time-savingsTransport Policy, 2021
- Tradable permits to manage urban mobility: Market design and experimental implementationTransportation Research Part A: Policy and Practice, 2020
- Personalized incentives for promoting sustainable travel behaviorsTransportation Research Part C: Emerging Technologies, 2020
- Dynamic congestion pricing with day-to-day flow evolution and user heterogeneityTransportation Research Part C: Emerging Technologies, 2015
- Impact of heavy vehicles on surrounding traffic characteristicsJournal of Advanced Transportation, 2014
- Air pollution and health risks due to vehicle trafficScience of The Total Environment, 2013
- Pareto-improving congestion pricing and revenue refunding with multiple user classesTransportation Research Part B: Methodological, 2010
- Mixed MNL models for discrete responseJournal of Applied Econometrics, 2000
- An efficient approach to solving the road network equilibrium traffic assignment problemTransportation Research, 1975